Every major AWS incident, analyzed: a timestamped timeline, the root cause in plain language, who felt it, and whether it earned SLA credits.
A latent race condition in DynamoDB’s DNS management automation left the regional endpoint with an empty DNS record. Because half of AWS depends on DynamoDB in us-east-1, the failure cascaded into EC2 launches, Lambda, and NLB health checks for ~15 hours.
9 min read
A degradation in the subsystem that manages Lambda’s execution capacity caused elevated invocation error rates in us-east-1 for about three hours. Because Lambda sits inside so many AWS features - including STS and parts of the console - the blast radius reached far beyond “serverless” workloads.
6 min read
An automated scaling activity triggered unexpected behavior in the network connecting AWS’s internal control plane to the main network. The resulting congestion blinded AWS’s own monitoring, broke the consoles and EC2 APIs, and degraded services from SQS to Ring doorbells for about seven hours.
8 min read
A playbook command executed with a mistyped parameter removed far more S3 index capacity than intended in us-east-1. The subsystems needed a full restart - something S3 hadn’t done in years at that scale - and for ~4 hours, a huge share of the web (including AWS’s own status dashboard) broke.
7 min read
aws